© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12646
    Prev
    Next
    INDEX
    Explanations

    high school education and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    í
    1.71
    od
    1.63
    ması
    1.25
    iv
    1.24
    ib
    1.19
    い
    1.17
    ot
    1.16
    uées
    1.16
    になる
    1.14
    onerror
    1.14
    POSITIVE LOGITS
     hebat
    1.19
     algal
    1.16
     lwd
    1.13
     Архиви
    1.13
     gjennom
    1.10
    кан
    1.09
     نه
    1.06
     yks
    1.06
    ี
    1.06
     benthic
    1.05
    Activations Density 0.004%

    No Known Activations